Intelligent Monitoring Method and System for Thermal Shock Chamber

Abstract

The present invention relates to the technical field of monitoring of thermal shock chambers, and particularly to an intelligent monitoring method and system for a thermal shock chamber. The method includes the following steps: monitoring the real-time operating state of the thermal shock chamber, and mining the transient state characteristics at each time point one by one to generate the transient state characteristics of each time node; performing transient mutation analysis on the transient state characteristics of each time node, and performing cold and hot alternating temperature fluctuation analysis to generate cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; performing state alternating transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters, and performing dynamic transition trend evolution to generate a cold and hot alternating state trend evolution map; obtaining the operation log of the thermal shock chamber. The present invention realizes efficient and accurate fault analysis and prediction of the thermal shock chamber.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring of thermal shock chambers, and particularly to an intelligent monitoring method and system for a thermal shock chamber. Background Art

[0002] In today's highly automated manufacturing environment, the thermal shock chamber, as a key environmental simulation test device, plays an important role in product reliability verification. This device simulates the harsh environmental conditions that a product may encounter during actual use by applying severe temperature cycles to the product, thereby effectively evaluating the product's resistance to temperature shock. However, due to its special operating nature and long-term thermal and cold alternation experiments, the probability of a thermal shock chamber malfunctioning is relatively high. Traditional monitoring methods for thermal shock chambers usually rely on manual observation and manual recording, suffering from problems such as low monitoring efficiency and inaccurate prediction of failure probabilities. With the in-depth development of industrial automation, higher requirements are put forward for the intelligent monitoring of thermal shock chambers. Therefore, there is an urgent need for a more intelligent monitoring method for thermal shock chambers. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes an intelligent monitoring method and system for a thermal shock chamber to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides an intelligent monitoring method for a thermal shock chamber, including the following steps:

[0005] Step S1: Monitor the real-time operating state of the thermal shock chamber, and mine the transient state characteristics at each time point one by one to generate the transient state characteristics at each time node;

[0006] Step S2: Conduct transient mutation analysis on the transient state characteristics at each time node, and conduct thermal and cold alternation temperature fluctuation analysis to generate cold state temperature fluctuation parameters and hot state temperature fluctuation parameters;

[0007] Step S3: Conduct state alternation transition analysis on the cold state temperature fluctuation parameters and hot state temperature fluctuation parameters, and conduct dynamic transition trend evolution to generate a thermal and cold alternation state trend evolution map;

[0008] Step S4: Obtain the operation log of the thermal shock chamber; conduct thermal and cold alternation shock simulation on the thermal and cold alternation state trend evolution map according to the operation log of the thermal shock chamber, and conduct time series state response recognition to construct thermal and cold alternation response maps for multiple time periods;

[0009] Step S5: Calculate the temperature rise amplitude of the thermal and cold alternation response maps for multiple time periods, and conduct abnormal state positioning to mark abnormal time periods;

[0010] Step S6: Predict the abnormal failure probability for the abnormal time period, make an abnormal failure diagnosis decision, and construct a failure decision strategy for the thermal shock chamber to perform real-time status monitoring of the thermal shock chamber.

[0011] The present invention helps to immediately understand the working conditions of the equipment by real-time monitoring the operating status of the thermal shock chamber, discover problems in a timely manner and take measures. Mining transient state characteristics at each time point can capture the instantaneous changes in the equipment state, providing detailed data support for subsequent analysis. Conducting transient mutation analysis helps to identify mutation situations in temperature changes, early warning of possible abnormal situations. Generating hot and cold alternating temperature fluctuation parameters can evaluate the temperature fluctuation situation, providing data support for subsequent status analysis and control. Analyzing the evolution trend of the hot and cold alternating state through the state trend evolution map helps to understand the transformation rules between different states, providing a basis for state prediction and regulation. The dynamic transition trend evolution helps to master the state change rules of the thermal shock chamber, providing a reference for equipment management and maintenance. Through hot and cold alternating shock simulation, the hot and cold changes in the real working environment can be simulated, evaluating the response ability and stability of the equipment. Constructing a hot and cold alternating response map helps to analyze the response situations in different time periods, discover abnormal responses and problems, and make timely adjustments. Calculating the temperature rise amplitude can quantify the temperature changes of the equipment during hot and cold alternation, helping to evaluate the stability and performance of the equipment. Abnormal state positioning can accurately locate the time period when the abnormality occurs, providing guidance for fault diagnosis and repair. Predicting the abnormal failure probability helps to early warning of possible problems, reducing losses caused by faults. Constructing a failure decision strategy for the shock chamber can guide the fault diagnosis decision, accelerating fault location and repair, and ensuring the stable operation of the equipment.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: Conduct real-time operating status monitoring of the thermal shock chamber and collect operating status monitoring parameters;

[0014] Step S12: Perform processing on abnormal missing values of the operating status monitoring parameters to obtain missing value filled operating status monitoring parameters;

[0015] Step S13: Perform multi-time point parameter sampling on the missing value filled operating status monitoring parameters to obtain operating status monitoring parameters at multiple time nodes;

[0016] Step S14: Mine transient state characteristics at each time point for the operating status monitoring parameters at multiple time nodes to generate transient state characteristics at each time node.

[0017] The present invention helps to timely capture the operating conditions of the equipment and discover potential problems in advance by real-time monitoring the operating status of the thermal shock chamber.

[0018] Collecting operation status monitoring parameters can provide comprehensive data support and lay a foundation for subsequent analysis and decision-making. Handling abnormal missing values helps ensure the integrity and accuracy of the data and avoid analysis errors caused by data missing.

[0019] The parameters after filling in the missing values can provide more complete and reliable status monitoring data and a more accurate basis for subsequent analysis. Conducting multi-time-point parameter sampling can capture the diversity and change trends of the equipment status and provide support for comprehensively understanding the equipment status.

[0020] Generating status monitoring parameters at multiple time nodes helps build a comprehensive status monitoring database and provides a data basis for subsequent analysis and comparison. Mining transient state characteristics at each time point can deeply understand the state characteristics of each time node and discover temporary changes and rules of the state.

[0021] Generating transient state characteristics helps identify key characteristics and trends of state changes and provides important clues for status monitoring and problem diagnosis.

[0022] Preferably, the specific steps of step S12 are as follows:

[0023] Detect abnormal status parameters from the operation status monitoring parameters and extract the abnormal status parameters;

[0024] Perform outlier removal processing based on the abnormal status parameters to obtain the status monitoring parameters after outlier removal;

[0025] Define the sliding window length value;

[0026] According to the sliding window length value, perform time series window partitioning on the status monitoring parameters after outlier removal to obtain status monitoring parameter sequences of multiple time windows;

[0027] Identify missing values in the status monitoring parameter sequences of multiple time windows and extract the parameter missing values of each time window;

[0028] Calculate the parameter average value of each dimension for the status monitoring parameters after outlier removal to obtain the parameter average value of each dimension;

[0029] Perform linear interpolation filling on the parameter missing values of each time window based on the parameter average value of each dimension to obtain the status monitoring parameters after missing value filling.

[0030] The present invention helps to identify parameters that may have problems by detecting and extracting abnormal state parameters, providing an important basis for subsequent processing. Extracting abnormal state parameters can help focus attention on parameters that may be abnormal, improving the efficiency of problem diagnosis. Removing outliers can improve data quality and accuracy, ensuring the reliability of subsequent analysis. Obtaining the abnormal removal state monitoring parameters helps to perform subsequent analysis and decision-making based on more reliable data. Dividing the time series window can segment the data by time, better capturing the trends and patterns of state changes. Generating the state monitoring parameter sequences of multiple time windows helps to analyze and compare the states of different time periods. Identifying the missing values of parameters in each time window helps to discover data missing situations, avoiding the impact of incomplete data on the analysis. Filling in the missing values can improve data integrity, ensuring the accuracy and reliability of subsequent analysis. Calculating the average value of parameters for each dimension helps to overall understand the trends and changes of parameters, providing a reference for subsequent analysis. Linear interpolation to fill in the missing values can effectively recover the missing data, ensuring data integrity and providing more reliable data support for subsequent analysis.

[0031] Preferably, the specific steps of step S2 are as follows:

[0032] Step S21: Perform a time series change analysis on the transient state characteristics of each time node to generate transient state change characteristic data;

[0033] Step S22: Perform a transient change time series fitting on the transient state change characteristic data to construct a transient change curve of the impact box;

[0034] Step S23: Perform a transient mutation analysis on the transient change curve of the impact box to mark the cold and hot alternating change timestamps;

[0035] Step S24: Perform a cold and hot alternating temperature fluctuation analysis on the transient state characteristics of each time node based on the cold and hot alternating change timestamps, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters.

[0036] The analysis of temporal variations in the present invention helps to explore the changing trends of transient state characteristics over time, reveals the regularity of state changes, and generating transient state change characteristic data can provide a detailed description of state changes, providing a data basis for subsequent analysis. By fitting the transient change time series, the data can be integrated into a continuous curve to better display the trends and characteristics of state changes. Constructing the transient change curve of the shock box helps to visually display the process of state changes, providing support for subsequent analysis and visualization. Transient mutation analysis can help identify mutation points in state changes, marking key timestamps helps to record the critical moments of state changes, and marking the timestamps of cold and hot alternating changes helps to identify the periodicity of temperature changes, providing a basis for subsequent temperature fluctuation analysis. Temperature fluctuation analysis can reveal the temperature change law under cold and hot alternating states, helping to understand the operating state of the device. Generating the temperature fluctuation parameters of the cold state and the hot state helps to evaluate the stability and performance of the device, providing a reference basis for device maintenance and optimization.

[0037] Preferably, the specific steps of step S3 are as follows:

[0038] Step S31: Calculate the peak-valley interval of the transient change curve of the shock box to obtain the cold and hot alternating cycle period;

[0039] Step S32: Calculate the mutation frequency of the transient change curve of the shock box to obtain the cold and hot alternating frequency within the period;

[0040] Step S33: Based on the cold and hot alternating frequency within the period, conduct logical mining of the alternating transformation of the cold and hot alternating cycle period to generate the cold and hot alternating transformation law;

[0041] Step S34: Conduct state alternating transition analysis on the temperature fluctuation parameters of the cold state and the temperature fluctuation parameters of the hot state to generate the transition characteristic of the alternating process parameters;

[0042] Step S35: Dynamically evolve the transition trend of the transition characteristic of the alternating process parameters according to the cold and hot alternating transformation law to generate the cold and hot alternating state trend evolution map.

[0043] By calculating the peak-valley interval, the present invention can reveal the periodicity of the transient change curve of the shock box, helping to understand the cycle of the cold and heat alternating cycle. Obtaining the cold and heat alternating cycle is helpful to determine the frequency and regularity of the state change, providing a basis for subsequent analysis. Calculating the mutation frequency can quantify the change frequency in the transient change curve of the shock box, helping to understand the speed and frequency of the state change. Obtaining the cold and heat alternating frequency within the cycle is helpful to evaluate the speed of the state change, providing important data support for subsequent analysis. By logically mining the cold and heat alternating transformation rule, it can help to understand the mechanism and regularity of the state transition, providing an in-depth understanding for state monitoring. Generating the cold and heat alternating transformation rule is helpful to predict future state changes, providing guidance for equipment maintenance and management. Conducting state alternating transition analysis can reveal the change characteristics of parameters under the cold and heat alternating state, helping to understand the process of state transition. Generating the transition characteristics of the alternating process parameters is helpful to quantify the process of state change, providing a detailed description for state monitoring and analysis. Conducting dynamic trend evolution analysis on the transition characteristics according to the cold and heat alternating transformation rule can help to understand the evolution process of the state. Generating the cold and heat alternating state trend evolution map is helpful to visually display the trend and regularity of the state change, providing visual support for decision-making.

[0044] Preferably, the specific steps of step S4 are as follows:

[0045] Step S41: Obtain the operation log of the thermal shock box;

[0046] Step S42: Calculate the remaining number of cold and heat alternations for the operation log of the thermal shock box to obtain the remaining number of operation alternations;

[0047] Step S43: Perform cold and heat alternating shock simulation on the cold and heat alternating state trend evolution map according to the remaining number of operation alternations, and collect multi-period parameters to generate cold and heat alternating simulation data for multiple time periods;

[0048] Step S44: Identify the time-series state response for the cold and heat alternating simulation data for multiple time periods, and construct cold and heat alternating response diagrams for multiple time periods.

[0049] By obtaining the operation log of the thermal shock chamber, the present invention can record the operation status and historical data of the device, providing a basis for subsequent analysis. The information contained in the operation log can be used to understand the operation conditions, fault conditions, etc. of the device, which is helpful for device management and maintenance. Calculating the remaining number of thermal and cold alternations can help predict the lifespan and remaining operation cycle of the device, providing a reference for device maintenance and planning. Obtaining the remaining number of operation alternations helps evaluate the health status of the device and take corresponding maintenance measures in a timely manner. Conducting thermal and cold alternation shock simulations can simulate the response of the device under different working conditions, helping to understand the performance of the device. Multi-period parameter acquisition can obtain thermal and cold alternation simulation data at different time periods, providing support for diversified analysis. Identifying the time-series state response of the thermal and cold alternation simulation data can help understand the response of the device under different conditions and the regularity of state changes. Constructing thermal and cold alternation response diagrams for multiple time periods helps compare the device responses at different time periods, providing more detailed data support for condition monitoring and analysis.

[0050] Preferably, the specific steps of step S5 are as follows:

[0051] Step S51: Mine the temperature states of each time period for the thermal and cold alternation response diagrams of multiple time periods, and extract the temperature state characteristics of each time period;

[0052] Step S52: Calculate the temperature rise amplitude for the temperature state characteristics of each time period to generate the temperature rise amplitude of each time period;

[0053] Step S53: Analyze the abnormal temperature changes for the temperature rise amplitude of each time period to obtain abnormal temperature change data;

[0054] Step S54: Locate the abnormal states based on the abnormal temperature change data and mark the abnormal time periods.

[0055] By mining the temperature state characteristics for each time period, the present invention can help understand the variation law of temperature within each time period, provide data support for anomaly detection. Extracting the temperature state characteristics of each time period helps identify the patterns and trends of temperature changes, providing a basis for subsequent analysis. Calculating the temperature rise amplitude for each time period can quantify the variation amplitude of temperature, helping to evaluate the working state and stability of the device. Generating the temperature rise amplitude data for each time period helps compare the temperature changes under different time periods, providing a reference for anomaly detection. Conducting abnormal temperature change analysis on the temperature rise amplitude can help detect abnormal conditions and timely discover problems in the device operation. Obtaining the abnormal temperature change data helps identify the characteristics of the abnormal state of the device, providing a basis for fault diagnosis and maintenance. Conducting abnormal state positioning based on the abnormal temperature change data can help accurately locate the abnormal problems of the device, guiding subsequent processing and maintenance. Marking the abnormal time periods helps monitor the device state changes in real time and take timely measures to avoid potential risks.

[0056] Preferably, the specific steps of step S6 are as follows:

[0057] Step S61: Conduct abnormal attribution inference on the abnormal time period to obtain the abnormal state factors;

[0058] Step S62: Predict the abnormal fault probability of the abnormal state factors to obtain the cold and heat alternating fault prediction probability;

[0059] Step S63: Conduct fault risk analysis based on the cold and heat alternating fault prediction probability, thereby generating alternating fault risk data;

[0060] Step S64: Make an abnormal fault diagnosis decision on the alternating fault risk data to construct an impact box fault decision strategy;

[0061] Step S65: Conduct intelligent monitoring and protection on the thermal shock chamber based on the impact box fault decision strategy to perform real-time state monitoring operations on the thermal shock chamber.

[0062] The present invention can help determine the cause and root cause of an anomaly by performing anomaly attribution inference on the abnormal time period, guiding subsequent processing measures. Obtaining the abnormal state factors helps to understand the possible problems and risk sources during the operation of the device. Predicting the probability of abnormal faults based on the abnormal state factors can help evaluate the likelihood of the device failing and make preparations in advance. Obtaining the prediction probability of thermal cycling faults helps to conduct risk assessment and formulate preventive measures. Analyzing the fault risk based on the prediction probability of thermal cycling faults can help identify the risks and problems that the device may face. Generating alternating fault risk data helps to formulate targeted fault prevention and treatment strategies. Making an abnormal fault diagnosis decision on the alternating fault risk data can help quickly and accurately handle the abnormal situation of the device, avoid the expansion of faults. Constructing a fault decision strategy for the shock chamber helps to improve the stability and reliability of the device, reduce downtime and maintenance costs. Intelligent monitoring and protection of the thermal shock chamber based on the fault decision strategy for the shock chamber can achieve real-time monitoring and protection of the device state. Performing real-time state monitoring operations on the thermal shock chamber helps to detect abnormal situations in a timely manner and take corresponding measures to ensure the safe operation and working efficiency of the device.

[0063] In this specification, an intelligent monitoring system for a thermal shock chamber is provided, which is used to execute the intelligent monitoring method for the thermal shock chamber as described above, and includes:

[0064] A transient feature mining module that monitors the real-time operating state of the thermal shock chamber, mines the transient state features at each time point one by one, and generates the transient state features of each time node;

[0065] A transient mutation module that performs transient mutation analysis on the transient state features of each time node and conducts thermal cycling temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters;

[0066] A dynamic transition trend module that performs state alternating transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters and conducts dynamic transition trend evolution, thereby generating a thermal cycling state trend evolution map;

[0067] A thermal cycling simulation module that obtains the operation log of the thermal shock chamber; performs thermal cycling shock simulation on the thermal cycling state trend evolution map according to the operation log of the thermal shock chamber, and conducts timing state response recognition to construct thermal cycling response diagrams for multiple time periods;

[0068] An abnormal state positioning module that calculates the temperature rise amplitude of the thermal cycling response diagrams for multiple time periods, conducts abnormal state positioning, and marks the abnormal time periods;

[0069] The fault diagnosis module predicts the probability of abnormal faults for abnormal time periods, makes decisions on abnormal fault diagnosis, constructs a fault decision strategy for the shock chamber, and performs real-time status monitoring operations on the thermal shock chamber.

[0070] The present invention helps to immediately discover potential problems by real-time monitoring the status of the thermal shock chamber, improves the response speed and equipment stability. Mining transient state characteristics at each time point can help understand the changes in the equipment operation status and provide data support for subsequent analysis. Transient mutation analysis can capture the mutation of temperature fluctuations, helps to timely discover abnormal fluctuations and conduct further research. The analysis of temperature fluctuations during the cold and hot alternation can reveal the temperature fluctuation characteristics in different states and provide a reference for state conversion. Conducting state alternation transition analysis helps to understand the temperature change trend between different states and provides an in-depth understanding of the state conversion mechanism. Generating a trend evolution map of the cold and hot alternation states can help real-time monitor the state evolution and provide a basis for prediction and intervention. Conducting cold and hot alternation shock simulation based on the operation log helps to simulate the real working environment and evaluate the performance of the equipment under different working conditions. Sequential state response recognition can help identify abnormal states and provide support for fault diagnosis and prevention. Calculating the temperature rise amplitude and locating abnormal states helps to accurately locate abnormal situations and improve the accuracy of fault location. Marking abnormal time periods can help monitor the occurrence of abnormal states and provide clues for further processing. Predicting the probability of abnormal faults and making diagnosis decisions helps to timely and accurately handle abnormal situations, reduce the impact of equipment failures on production. Constructing a fault decision strategy for the shock chamber can improve equipment maintenance efficiency and production stability, and ensure the safe operation of the equipment. Description of the Drawings

[0071] Figure 1 It is a schematic diagram of the step flow of an intelligent monitoring method for a thermal shock chamber of the present invention;

[0072] Figure 2 It is a schematic diagram of the detailed implementation steps of step S1;

[0073] Figure 3 It is a schematic diagram of the detailed implementation steps of step S2;

[0074] Figure 4 It is a schematic diagram of the detailed implementation steps of step S3. Detailed Implementation Manner

[0075] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0076] The embodiments of the present application provide an intelligent monitoring method and system for a thermal shock chamber. The execution subjects of the intelligent monitoring method and system for the thermal shock chamber include, but are not limited to, the following general computing nodes of the system: mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc. The data processing platform includes, but is not limited to, at least one of an audio and image management system, an information management system, and a cloud data management system.

[0077] Please refer to Figures 1 to 4 , the present invention provides an intelligent monitoring method for a thermal shock chamber. The intelligent monitoring method for the thermal shock chamber includes the following steps:

[0078] Step S1: Monitor the real-time operating status of the thermal shock chamber, and mine the transient state characteristics at each time point one by one to generate the transient state characteristics of each time node.

[0079] Step S2: Conduct transient mutation analysis on the transient state characteristics of each time node, and conduct cold and hot alternating temperature fluctuation analysis to generate cold state temperature fluctuation parameters and hot state temperature fluctuation parameters.

[0080] Step S3: Conduct state alternating transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters, and conduct dynamic transition trend evolution to generate a cold and hot alternating state trend evolution map.

[0081] Step S4: Obtain the operation log of the thermal shock chamber; perform cold and hot alternating shock simulation on the cold and hot alternating state trend evolution map according to the operation log of the thermal shock chamber, and conduct time series state response recognition to construct cold and hot alternating response maps for multiple time periods.

[0082] Step S5: Calculate the temperature rise amplitude of the cold and hot alternating response maps for multiple time periods, and locate the abnormal state to mark the abnormal time period.

[0083] Step S6: Predict the abnormal fault probability of the abnormal time period, and make an abnormal fault diagnosis decision to construct a fault decision strategy for the shock chamber to execute the real-time state monitoring operation of the thermal shock chamber.

[0084] The present invention helps to immediately understand the working condition of the equipment by monitoring the operating state of the thermal shock chamber in real time, discover problems in a timely manner and take measures. Mining transient state characteristics at each time point can capture the instantaneous changes in the equipment state, providing detailed data support for subsequent analysis. Conducting transient mutation analysis helps to identify mutation situations in temperature changes and give early warnings of possible abnormal situations. Generating cold and hot alternating temperature fluctuation parameters can evaluate the temperature fluctuation situation, providing data support for subsequent state analysis and control. Analyzing the evolution trend of the cold and hot alternating state through the state trend evolution map helps to understand the transformation rules between different states, providing a basis for state prediction and regulation. The dynamic transition trend evolution helps to master the state change rules of the thermal shock chamber, providing a reference for equipment management and maintenance. Through the simulation of cold and hot alternating shocks, the cold and hot changes in the real working environment can be simulated, and the response ability and stability of the equipment can be evaluated. Constructing a cold and hot alternating response map helps to analyze the response conditions in different time periods, discover abnormal responses and problems, and make timely adjustments. Calculating the temperature rise amplitude can quantify the temperature change of the equipment during the cold and hot alternation process, helping to evaluate the stability and performance of the equipment. Abnormal state positioning can accurately locate the time period when the abnormality occurs, providing guidance for fault diagnosis and repair. Predicting the probability of abnormal faults helps to give early warnings of possible problems and reduce losses caused by faults. Constructing a fault decision-making strategy for the shock chamber can guide fault diagnosis decisions, speed up fault location and repair, and ensure the stable operation of the equipment.

[0085] In an embodiment of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of an intelligent monitoring method for a thermal shock chamber of the present invention. In this example, the steps of the intelligent monitoring method for the thermal shock chamber include:

[0086] Step S1: Monitor the real-time operating state of the thermal shock chamber, and mine transient state characteristics at each time point to generate transient state characteristics at each time node;

[0087] In this embodiment, multiple sensors are installed in the thermal shock chamber to monitor key parameters in real time, such as temperature, humidity, air pressure, flow rate, etc. These sensors should have high precision and fast response capabilities. Select suitable monitoring devices, such as thermocouples, humidity sensors, and pressure sensors. Configure a data acquisition system to ensure that it can receive and store sensor data in real time. The system should support high-frequency data acquisition to capture transient state changes. Use a data acquisition card or an embedded system (such as Raspberry Pi or Arduino) for data acquisition. Start the thermal shock chamber and simultaneously start the data acquisition system to ensure that each sensor starts recording data in real time. Set the data recording frequency, for example, collect data once per second to capture transient changes. Clean the real-time collected data to remove noise and outliers to ensure data accuracy. Handle missing values and use interpolation or filling methods to ensure data continuity. Analyze the data at each time node, extract transient state features, and use time series analysis methods, such as the sliding window technique, to capture the change rate and trend at each time point. Organize the extracted transient features into a data set to form the transient state features at each time node. The data set should include timestamps and corresponding feature values for subsequent analysis. Use statistical analysis software (such as Pandas, NumPy in Python, or R) to analyze the transient feature data, identify the relationships and change trends between features, and apply machine learning or deep learning algorithms (such as clustering analysis, regression analysis) to further explore potential patterns.

[0088] Step S2: Perform transient mutation analysis on the transient state features at each time node and conduct cold and hot alternating temperature fluctuation analysis to generate cold state temperature fluctuation parameters and hot state temperature fluctuation parameters;

[0089] In this embodiment, use statistical methods (such as the Z-score, moving average, or CUSUM method) to detect the mutation points of temperature data, determine the criteria for mutation points. For example, when the temperature change rate exceeds a preset threshold, it is marked as a mutation state. Record the time, mutation amplitude (temperature change amount), and its duration of each mutation point. Classify the mutation characteristics to identify whether it is a cold mutation or a hot mutation for subsequent analysis. According to the mutation points, divide the temperature data into cold state segments and hot state segments. Each segment of data represents a temperature state (cold or hot). Calculate the fluctuation amplitude for the temperature data in the cold state and hot state respectively. Usually, the standard deviation or range is used to quantify the degree of fluctuation. Record the fluctuation amplitude of the cold state segment as the cold state temperature fluctuation parameter, and record the fluctuation amplitude of the hot state segment as the hot state temperature fluctuation parameter. Organize the cold state temperature fluctuation parameters and hot state temperature fluctuation parameters into a report, including the results of mutation analysis and fluctuation analysis, and provide data visualization (such as line charts, bar charts) to display the temperature fluctuation characteristics during the cold and hot alternation process for easy understanding and decision-making.

[0090] Step S3: Conduct state alternating transition analysis on the cold-state temperature fluctuation parameters and the hot-state temperature fluctuation parameters, and perform dynamic transition trend evolution to generate a cold-hot alternating state trend evolution map;

[0091] In this embodiment, the fluctuation parameters of the cold state and the hot state are sorted into time series data for subsequent analysis. Ensure that the timestamps correspond to the fluctuation parameters to form a unified data set. Determine the alternating conditions between the cold state and the hot state, usually based on the threshold or time period of temperature change. By analyzing the changes in the fluctuation parameters, identify the time points of transition from the cold state to the hot state and the time points of transition back from the hot state to the cold state. Record the time, duration, fluctuation amplitude, and change rate of each state alternation to form a characteristic data set of the alternating state for subsequent dynamic analysis. Use statistical methods and time series analysis techniques (such as moving average, exponential smoothing) to analyze the dynamic change trend of the fluctuation parameters, identify the rising, falling, and stable trends of the fluctuation parameters during the alternation process, establish a mathematical model (such as linear regression, polynomial regression) to fit the trend of the fluctuation parameters changing with time, apply the model to the entire time series data to predict the future fluctuation trend, use data visualization tools (such as Matplotlib, Seaborn, or Tableau) to draw the trend evolution map of the cold-hot state alternation. The map should display the changes in the fluctuation parameters, the alternating state markers, and the trend line in the time series, including the time axis, the fluctuation parameters (cold state and hot state), the alternating state indicators (such as marker points or shaded areas), and the trend line. Ensure that the map is clear and intuitive for understanding the dynamic changes during the cold-hot alternation process. Organize the results of the alternating transition analysis and the dynamic trend evolution into a report, including the map and the relevant data analysis.

[0092] Step S4: Obtain the operation log of the thermal shock chamber; conduct cold-hot alternating shock simulation on the cold-hot alternating state trend evolution map according to the operation log of the thermal shock chamber, and perform time-series state response identification to construct cold-hot alternating response maps for multiple time periods;

[0093] In this embodiment, the format and content of the operation log of the thermal shock chamber are determined, which usually include parameters such as operation time, temperature setting, actual temperature, humidity, pressure, current, etc. The historical operation log is extracted from the control system or data recording system of the thermal shock chamber to ensure the integrity and accuracy of the data. The log data should cover a certain time range for subsequent analysis. The collected operation logs are sorted in chronological order to ensure that the timestamps of each record are consistent. The data is cleaned to remove unnecessary fields and invalid records. According to the operation log, the initial conditions for simulation are set, including the temperature change range, duration, and frequency of hot and cold alternation. The time step for simulation is determined to capture subtle state changes. A computer simulation software (such as MATLAB, Simulink, or a custom simulation tool) is used to simulate the hot and cold alternation state to generate shock response data. During the simulation process, the state parameters such as temperature and humidity at each time node are recorded to reflect the impact of hot and cold alternation. The time-series state response data is extracted from the simulation results, and the changes in temperature, humidity, and other key parameters during the hot and cold alternation process are focused on. Time series analysis methods are used to identify the change patterns of each state parameter during the hot and cold alternation process and evaluate their response characteristics. Statistical methods such as the autocorrelation function (ACF) and partial autocorrelation function (PACF) are used to analyze the time-series characteristics of the response data. According to the simulation results and operation log, multiple time periods are reasonably divided, usually based on the duration of the cold state and the hot state. Each time period should represent a complete hot and cold alternation cycle. A data visualization tool (such as Matplotlib, Seaborn, or Excel) is used to plot the hot and cold alternation response diagrams for multiple time periods. The diagrams should include the changes in state parameters (such as temperature and humidity) for each time period and mark the start and end times of the alternation state. Ensure that the response diagrams are clear and intuitive, capable of showing the hot and cold alternation state and the corresponding parameter fluctuations within each time period. The generated diagrams should be convenient for observing the relationship between the hot and cold alternation and its impact on the equipment performance and the environment. The simulation results and response diagrams are sorted out to form a complete analysis report, recording the results of the hot and cold alternation shock simulation and the time-series state response.

[0094] Step S5: Calculate the temperature rise amplitude of the hot and cold alternation response diagrams for multiple time periods, locate abnormal states, and mark abnormal time periods;

[0095] In this embodiment, key temperature data is extracted from the cold and heat alternating response graph to ensure the integrity and representativeness of the data. The temperature changes in each time period are recorded, including the highest temperature, the lowest temperature, and the average temperature at each time node. The extracted temperature data is organized in a time series format for subsequent analysis, including the time stamp, the temperature value, and the identifier of the time period to which it belongs. The temperature rise amplitude is usually defined as the temperature change amplitude within a specific time period. For each time period, the corresponding temperature rise amplitude is calculated and the result is recorded. The calculation results are organized into a table, including the time period identifier, the highest temperature, the lowest temperature, and the temperature rise amplitude. According to industry standards or historical data, an abnormal threshold for the temperature rise amplitude is defined. For example, if the temperature rise amplitude exceeds a certain specific value (such as 10°C), it is regarded as an abnormal state. The calculated temperature rise amplitude data is traversed to identify the time periods that exceed the abnormal threshold, and the start time and end time of the abnormal state are recorded. Using logical conditions for screening, the detected abnormal time periods are marked on the cold and heat alternating response graph. Different colors or marking symbols can be used to highlight the abnormal areas to ensure that the markings are clearly visible for subsequent analysis and discussion. The calculation results of the temperature rise amplitude and the positioning results of the abnormal state are organized to form a complete analysis report. The report should include the abnormal time periods, the temperature rise amplitude data, and the corresponding graphical representations.

[0096] Step S6: Predict the abnormal failure probability for the abnormal time periods and make an abnormal failure diagnosis decision, and construct a shock box failure decision strategy to perform real-time status monitoring operations on the thermal shock box.

[0097] In this embodiment, relevant data is extracted from the obtained abnormal time period records, including abnormal temperature rise amplitude, duration, operation logs, etc., and organized into structured data for subsequent analysis. Characteristic variables for fault probability prediction are determined, such as temperature fluctuation amplitude, ambient humidity, operation time, equipment load, etc., to ensure the integrity and accuracy of the data, so as to improve the effect of the prediction model. According to the data characteristics, a suitable fault prediction model can be considered, such as: statistical models (such as logistic regression), machine learning models (such as random forest, support vector machine, decision tree), deep learning models (such as neural network). Determine the input and output of the model. Usually, the output is the probability of a fault occurring. The collected historical data is divided into a training set and a test set. Usually, 70% of the data is used for training and 30% of the data is used for verification. The selected model is trained using the training set, and the model parameters are adjusted to improve the prediction accuracy. The performance of the model is evaluated on the test set, and metrics such as accuracy, recall, and F1-score are used to evaluate the prediction ability of the model. According to the results of the abnormal fault probability prediction, fault diagnosis decision rules are formulated. For example: if the fault probability exceeds a certain threshold (such as 70%), a fault alarm is triggered. Combining the operating status of the equipment and historical fault records, corresponding maintenance measures are determined. A complete set of fault decision strategies is designed, including fault early warning, response measures, and subsequent maintenance plans. Considering the operating environment and usage frequency of the equipment, a personalized maintenance strategy is formulated.

[0098] In this embodiment, refer to Figure 2 , which is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0099] Step S11: Monitor the real-time operating status of the thermal shock chamber and collect operating status monitoring parameters;

[0100] Step S12: Perform abnormal missing value filling processing on the operating status monitoring parameters to obtain the missing value filled status monitoring parameters;

[0101] Step S13: Perform multi-time point parameter sampling on the missing value filled status monitoring parameters to obtain the status monitoring parameters at multiple time nodes;

[0102] Step S14: Mine the transient state characteristics of each time point for the status monitoring parameters at multiple time nodes to generate the transient state characteristics of each time node.

[0103] In this embodiment, ensure that the thermal shock chamber is equipped with necessary sensors, including temperature sensors, humidity sensors, pressure sensors, and vibration sensors, to ensure that these parameters can be monitored in real time. Configure a data acquisition system (such as a PLC or a data acquisition card) to ensure that it can receive and store the real-time data from the sensors. Start the operation program of the thermal shock chamber, activate the monitoring system, and start real-time acquisition of the operation status parameters. During the operation, regularly collect the status monitoring parameters and record them, including timestamps, temperature, humidity, pressure, etc., to ensure that the data is collected at a preset frequency (such as every second or every minute). Conduct a preliminary analysis of the collected operation status monitoring parameters to identify missing values. You can use the Pandas library in a programming language (such as Python) and use the isnull() function to detect missing data. Combine statistical methods (such as the Z-score or IQR method) to identify outliers to avoid introducing incorrect data when filling in the missing values. Select a suitable method for filling in the missing values. Common methods include: Mean filling: Fill in the missing values with the mean of this parameter. Interpolation method: Use methods such as linear interpolation or polynomial interpolation to fill in according to adjacent data points. KNN filling: Use the K-nearest neighbor algorithm to fill in the missing values according to similar samples. Process the missing values using the selected filling method to generate the status monitoring parameters with missing values filled in, ensuring that the filled data is in the same format as the original data. According to the experimental requirements and data characteristics, set a suitable sampling frequency (such as every minute or every hour) to ensure that sufficient samples are obtained for subsequent analysis. Determine multiple time nodes for sampling. For example, select key operation cycles or state change points. Extract the data at the specified time nodes from the status monitoring parameters with missing values filled in to generate a set of status monitoring parameters for multiple time nodes. Define the definition of transient state characteristics, such as transient response time, maximum value, minimum value, mean value, standard deviation, etc. These characteristics will be used to analyze the trends and patterns of state changes. Select a suitable feature extraction method, such as: Time series analysis: Use the autocorrelation function (ACF) and partial autocorrelation function (PACF) to analyze the time correlation of the data. Fourier transform: Used for frequency domain analysis to identify periodic characteristics. Wavelet transform: Suitable for extracting transient signal characteristics to identify mutations or changes. Mine the transient state characteristics one by one for the status monitoring parameters of each time node, and calculate and record the relevant characteristic values.

[0104] In this embodiment, the specific steps of step S12 are as follows:

[0105] Detect the abnormal state parameters from the operation status monitoring parameters and extract the abnormal state parameters;

[0106] Based on the abnormal state parameters, perform outlier rejection processing to obtain the status monitoring parameters after outlier rejection;

[0107] Define the sliding window length value;

[0108] Perform a time series window division on the anomaly rejection status monitoring parameters according to the sliding window length value to obtain the status monitoring parameter sequences of multiple time windows;

[0109] Identify missing values in the status monitoring parameter sequences of multiple time windows, and extract the parameter missing values of each time window;

[0110] Perform an average calculation of the parameters of each dimension for the anomaly rejection status monitoring parameters to obtain the parameter average value of each dimension;

[0111] Perform linear interpolation filling on the parameter missing values of each time window based on the parameter average value of each dimension to obtain the status monitoring parameters with missing values filled;

[0112] In this embodiment, select a suitable anomaly detection method. For example: Statistical method: Use the mean and standard deviation to determine the threshold (such as mean ± 3×standard deviation) to identify outliers. Machine learning method: Use IsolationForest or Support Vector Machine (SVM) for anomaly detection. Apply the selected anomaly detection method to mark and extract the anomaly status parameters, visualize the data to help identify anomalies. According to the detected anomaly status parameters, remove these outliers to generate the anomaly rejection status monitoring parameters. Use programming tools (such as the Pandas library in Python) for data cleaning, and use dropna() or conditional filtering to remove outliers. According to the data characteristics and analysis requirements, define the length of the sliding window. For example, a fixed length (such as 10 data points) or a time-based window (such as 1 minute) can be selected. According to the defined sliding window length value, perform a time series window division on the anomaly rejection status monitoring parameters, which can be achieved using the rolling() method of Pandas. The data within each window forms a new sequence for subsequent analysis. Identify missing values in the status monitoring parameter sequences of each time window, and the isnull() function can be used to mark the missing data, record the position and quantity of the missing values in each time window for subsequent processing. Perform an average calculation on the status monitoring parameters of each dimension. Within each time window, use the mean() function to calculate the mean value of each parameter, and store the average value of each dimension in a new data structure for subsequent filling of missing values. Select the linear interpolation method to fill the missing values. Linear interpolation predicts the missing values through the linear relationship of known data points. Perform linear interpolation filling on the missing values of each time window using the previously calculated parameter average value, which can be achieved using the interpolate() method of Pandas to ensure that the interpolated data maintains the time order and format of the original sequence.

[0113] In this embodiment, refer to Figure 3 as the schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0114] Step S21: Perform a temporal variation analysis on the transient state characteristics at each time node to generate transient state change characteristic data;

[0115] Step S22: Perform a transient change temporal fitting on the transient state change characteristic data to construct a transient change curve of the shock box;

[0116] Step S23: Perform a transient mutation analysis on the transient change curve of the shock box to mark the cold and hot alternating change timestamps;

[0117] Step S24: Perform a cold and hot alternating temperature fluctuation analysis on the transient state characteristics at each time node based on the cold and hot alternating change timestamps, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters.

[0118] In this embodiment, the transient state characteristic data is organized into a time series format to ensure that the characteristics corresponding to each time node can be listed in sequence. Select a suitable temporal variation analysis method, such as: Trend analysis: Use the moving average or exponential smoothing method to analyze the data trend. Rate of change calculation: Calculate the rate of change at each time node (such as the relative change percentage). Analyze the transient state characteristics at each time node, record the change characteristics (such as rising, falling, fluctuating, etc.), and generate transient state change characteristic data. According to the characteristics of the transient state change characteristics, select a suitable fitting model, for example: Linear regression: Suitable for linear change trends. Polynomial regression: Suitable for complex change curves. Smoothing spline fitting: Suitable for smooth fitting of non-linear data. Use a fitting algorithm (such as the regression model in Scikit-learn or the interpolation method in SciPy) to fit the transient state change characteristic data to generate a transient change curve. Evaluate the accuracy of the fitting result, for example, judge the fitting effect by the coefficient of determination R² or the root mean square error (RMSE). Select a suitable mutation detection algorithm, such as: CUSUM (Cumulative Sum Control Chart): Used to detect changes in the mean value. Gradient change detection: Analyze the rate of change to identify mutation points. Input the transient change curve into the selected mutation detection algorithm to identify and mark the transient mutation points, which usually correspond to the cold and hot alternating change timestamps. Extract the marked cold and hot alternating change timestamps from the previous steps for subsequent analysis. According to the cold and hot alternating change timestamps, divide the transient state characteristic data into cold state and hot state data sets. Select a suitable fluctuation analysis method, for example: Standard deviation calculation: Measure the dispersion degree of temperature fluctuations. Range analysis: Calculate the maximum and minimum values in each state to identify the fluctuation range. Perform a temperature fluctuation analysis on the cold state data set to calculate the cold state temperature fluctuation parameters (such as mean, standard deviation, maximum, and minimum values). Perform a temperature fluctuation analysis on the hot state data set to calculate the hot state temperature fluctuation parameters.

[0119] In this embodiment, refer to Figure 4 , which is a schematic diagram of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0120] Step S31: Calculate the peak-valley interval of the transient change curve of the shock box to obtain the cold and hot alternating cycle period;

[0121] Step S32: Calculate the mutation frequency of the transient change curve of the shock box to obtain the cold and hot alternating frequency within the period;

[0122] Step S33: Mine the alternating transformation logic for the cold and hot alternating cycle period based on the cold and hot alternating frequency within the period, so as to generate the cold and hot alternating transformation rule;

[0123] Step S34: Conduct a state alternating transition analysis on the cold state temperature fluctuation parameter and the hot state temperature fluctuation parameter, so as to generate the transition characteristic of the alternating process parameter;

[0124] Step S35: Evolve the dynamic transition trend of the transition characteristic of the alternating process parameter according to the cold and hot alternating transformation rule, so as to generate the cold and hot alternating state trend evolution map.

[0125] In this embodiment, a suitable peak-valley detection algorithm is used. For example, find_peaks in the SciPy library is used to detect the local maxima (peaks) and local minima (valleys) of a curve. The selected peak-valley detection algorithm is applied to mark each peak and valley in the change curve. By calculating the time difference between adjacent peaks, the cold-hot alternating cycle period can be obtained. Simple difference calculation (such as time[i + 1] - time[i]) can be used to record the duration of each cycle. The mutation frequency represents the occurrence frequency of mutation events (peaks or valleys) within a specific time period. Within the calculated cold-hot alternating cycle, the total number of mutations (peaks and valleys) is counted. The mutation frequency = cycle duration / number of mutations. The mutation frequency within each cycle is recorded. Data mining techniques (such as association rule learning or classification algorithms) are used to identify the alternating transformation pattern. The selected method is applied to analyze the frequency data to extract the cold-hot alternating transformation pattern. For example, the Apriori algorithm is used to discover frequent item sets, or a decision tree model is used for classification. A suitable analysis method is selected, such as: the Markov model, which is used to analyze the transition probability between states; time series analysis, which analyzes the change trend of fluctuation parameters. The fluctuation parameters of the cold state and the hot state are analyzed, and the transition characteristics between states (such as transition probability, average duration, etc.) are calculated to generate the transition characteristics of the alternating process parameters. The alternating process parameter characteristics are extracted from the previous steps to prepare for the dynamic trend evolution. A suitable model (such as a time series prediction model, a neural network model) is selected for dynamic trend evolution analysis. Based on the cold-hot alternating transformation pattern and the extracted alternating process characteristics, the future state changes are calculated and predicted, and a cold-hot alternating state trend evolution map is drawn. This can be achieved using visualization tools (such as Matplotlib or Tableau).

[0126] In this embodiment, step S4 includes the following steps:

[0127] Step S41: Obtain the operation log of the thermal shock chamber;

[0128] Step S42: Calculate the remaining number of cold-hot alternations for the operation log of the thermal shock chamber to obtain the remaining number of operating alternations;

[0129] Step S43: Perform cold-hot alternating shock simulation on the cold-hot alternating state trend evolution map according to the remaining number of operating alternations, and collect multi-period parameters to generate cold-hot alternating simulation data for multiple time periods;

[0130] Step S44: Identify the time-series state response for the cold-hot alternating simulation data for multiple time periods, and construct cold-hot alternating response maps for multiple time periods.

[0131] In this embodiment, determine the storage location of the operation log of the thermal shock chamber, which is usually the built-in control system, data recorder or server of the device. Use appropriate tools (such as SQL queries, API interfaces or file reading) to extract the operation log. The log content should include key information such as timestamps, operating status, temperature, pressure, humidity, etc. Define the thermal alternation clearly, for example, the change between the set cold state and hot state each time the temperature reaches. By analyzing the operation log, count the number of thermal alternations since the device was started, and calculate the remaining number of alternations according to the design and usage cycle of the device. Use a simple counting algorithm to traverse the log data and accumulate alternation events. According to the remaining number of operating alternations, set the simulated time period and specific parameters for each time period (such as temperature range, time interval, shock frequency). Select a suitable simulation method, for example: Numerical simulation: Use computational fluid dynamics (CFD) software for heat conduction and fluid flow simulation. Discrete event simulation: Simulate the process of each alternation event. Perform thermal shock simulation of thermal alternation according to the set parameters, and record the state change data within each time period. Professional simulation software (such as ANSYS, MATLAB Simulink) can be used to achieve this. During the simulation process, regularly collect key parameters (such as temperature, pressure, humidity) to generate thermal alternation simulation data for multiple time periods. Organize the thermal alternation simulation data of each time period into a structured time series format to ensure that the data for each time period is clearly available. Select a suitable method for identifying the time series state response, for example: Time series analysis: Use the autoregressive moving average (ARMA) model for analysis. Machine learning method: Use classification algorithms (such as decision trees, random forests) for state identification. Identify the state response of the simulation data for multiple time periods, and extract the thermal alternation response characteristics for each time period. Plot the identified response characteristics into a graph to generate thermal alternation response graphs for multiple time periods. This can be plotted using visualization tools (such as Matplotlib, Tableau).

[0132] In this embodiment, step S5 includes the following steps:

[0133] Step S51: Mine the temperature state for each time period of the thermal alternation response graphs for multiple time periods, and extract the temperature state characteristics for each time period;

[0134] Step S52: Calculate the temperature rise amplitude for the temperature state characteristics of each time period to generate the temperature rise amplitude for each time period;

[0135] Step S53: Analyze the abnormal temperature changes for the temperature rise amplitude of each time period to obtain abnormal temperature change data;

[0136] Step S54: Locate the abnormal state based on the abnormal temperature change data and mark the abnormal time periods.

[0137] In this embodiment, temperature state characteristics are defined, including but not limited to: maximum temperature: the maximum temperature value within each time period; minimum temperature: the minimum temperature value within each time period; average temperature: the average temperature within the time period; temperature volatility: the standard deviation of the temperature. Calculate the above characteristics for the temperature data of each time period to extract the temperature state characteristics of each time period, which can be achieved through programming tools (such as the Pandas library in Python). The temperature rise amplitude refers to the temperature change within the time period and can be defined as: temperature rise amplitude = maximum temperature - minimum temperature. Alternatively, it can also be calculated based on the average temperature change of the time period. Perform the temperature rise amplitude calculation on the temperature state characteristics of each time period to obtain the temperature rise amplitude data for each time period. Determine the standard for abnormal temperature changes, for example, use statistical methods (such as Z-score) to identify values that are significantly different from the average temperature rise amplitude. A common strategy is to set a threshold, for example: abnormal threshold = average temperature rise amplitude + k × standard deviation, where k usually takes a value of 2 or 3. Analyze the temperature rise amplitude of each time period, mark the temperature rise amplitudes that exceed the abnormal threshold, record the abnormal temperature change data, and use the conditional filtering function in Pandas to extract the abnormal values. According to the analysis results, mark the time periods corresponding to the identified abnormal temperature changes. An identification column can be added to the dataset to record whether each time period is in an abnormal state. Record the marked abnormal time periods in the report, describing the specific situation and possible reasons for the abnormality. The report should include: the time period when the abnormality occurred, the temperature rise amplitude of the abnormality, possible failure reasons or recommended follow-up measures.

[0138] In this embodiment, step S6 includes the following steps:

[0139] Step S61: Conduct abnormal attribution inference on the abnormal time period to obtain abnormal state factors;

[0140] Step S62: Predict the abnormal failure probability of the abnormal state factors to obtain the cold and heat alternation failure prediction probability;

[0141] Step S63: Perform failure risk analysis based on the cold and heat alternation failure prediction probability to generate alternation failure risk data;

[0142] Step S64: Make an abnormal failure diagnosis decision on the alternation failure risk data to construct an impact chamber failure decision strategy;

[0143] Step S65: Perform intelligent monitoring and protection on the thermal shock chamber based on the impact chamber failure decision strategy to execute the real-time status monitoring operation of the thermal shock chamber.

[0144] In this embodiment, a suitable attribution analysis method is adopted. For example: Root Cause Analysis (RCA): Identify the root cause leading to the anomaly. Causal relationship model: Use data-driven methods (such as Bayesian networks) to establish causal relationships. Apply the selected analysis method to analyze the abnormal data and identify the abnormal state factors, which may include equipment failures, external environmental changes, or improper operations, etc. Document the identified abnormal state factors to form an attribution analysis report. Select a suitable probability prediction model according to the data characteristics and requirements. For example: Logistic regression: Suitable for binary classification problems. Random forest: Suitable for complex non-linear relationships. Support Vector Machine (SVM): Suitable for the classification of high-dimensional data. Use the abnormal state factors obtained from the attribution analysis to construct a training dataset, including input features and target variables (labels of whether there is a failure or not). Use the selected model to train the data, adjust the model parameters to optimize the prediction effect. Apply the trained model to a new dataset to predict the failure probability of each state, generate the hot and cold alternating failure prediction probability. Select a suitable risk assessment model. For example: Fault Tree Analysis (FTA): Used for system failure analysis. Markov model: Analyze the probability of state transition. Based on the predicted failure probability, calculate the risk value of each failure, generate alternating failure risk data. Record the risk assessment results in the database, including the risk level of each failure, possible impacts, and recommended countermeasures. Select a suitable decision support model. For example: Decision tree: Used to visualize the decision-making process. Fuzzy logic control: Handle uncertainty and ambiguity. According to the alternating failure risk data, formulate a fault diagnosis decision strategy, identify high-risk faults and propose corresponding preventive measures. Design the architecture of the intelligent monitoring system, including data acquisition, processing, and analysis modules. Deploy sensors and data acquisition devices to monitor the running state of the thermal shock chamber in real time, collect key parameters (such as temperature, pressure, humidity, etc.). Analyze the real-time data through the data processing module to identify abnormal states and potential faults in a timely manner. Automatically execute monitoring and protection measures according to the fault decision strategy. For example: Alarm system: Send an alarm in time when an anomaly is detected. Automatic adjustment: Automatically adjust the running parameters of the equipment when conditions permit to reduce the risk of failure.

[0145] In this embodiment, an intelligent monitoring system for a thermal shock chamber is provided, which is used to execute the intelligent monitoring method for the thermal shock chamber as described above, and includes:

[0146] A transient feature mining module monitors the real-time running state of the thermal shock chamber and mines the transient state features at each time point, generating the transient state features of each time node.

[0147] A transient mutation module performs transient mutation analysis on the transient state features of each time node and conducts hot and cold alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters.

[0148] A dynamic transition trend module analyzes the state alternating transition of cold-state temperature fluctuation parameters and hot-state temperature fluctuation parameters, and conducts dynamic transition trend evolution to generate a trend evolution map of cold-hot alternating states;

[0149] A cold-hot alternating simulation module obtains the operation log of the thermal shock chamber; based on the operation log of the thermal shock chamber, it conducts cold-hot alternating shock simulation on the trend evolution map of cold-hot alternating states, and conducts timing state response recognition to construct cold-hot alternating response maps for multiple time periods;

[0150] An abnormal state positioning module calculates the temperature rise amplitude of the cold-hot alternating response maps for multiple time periods, and conducts abnormal state positioning to mark abnormal time periods;

[0151] A fault diagnosis module predicts the probability of abnormal faults for abnormal time periods, and makes abnormal fault diagnosis decisions to construct a fault decision strategy for the shock chamber to perform real-time status monitoring operations on the thermal shock chamber.

[0152] The present invention helps to immediately discover potential problems by real-time monitoring the status of the thermal shock chamber, improves the response speed and equipment stability. Mining transient state characteristics at each time point can help understand the changes in the equipment operation status and provide data support for subsequent analysis. Transient mutation analysis can capture the mutation of temperature fluctuations, helps to promptly discover abnormal fluctuations and conduct further research. Cold-hot alternating temperature fluctuation analysis can reveal the temperature fluctuation characteristics in different states, provide a reference for state conversion. Conducting state alternating transition analysis helps to understand the temperature change trend between different states and provides an in-depth understanding of the state conversion mechanism. Generating a trend evolution map of cold-hot alternating states can help to real-time monitor the state evolution and provide a basis for prediction and intervention. Conducting cold-hot alternating shock simulation based on the operation log helps to simulate the real working environment and evaluate the performance of the equipment under different working conditions. Timing state response recognition can help to identify abnormal states and provide support for fault diagnosis and prevention. Calculating the temperature rise amplitude and abnormal state positioning helps to accurately locate abnormal situations and improve the accuracy of fault location. Marking abnormal time periods can help to monitor the occurrence of abnormal states and provide clues for further processing. Predicting the probability of abnormal faults and making diagnosis decisions helps to promptly and accurately handle abnormal situations and reduce the impact of equipment failures on production. Constructing a fault decision strategy for the shock chamber can improve equipment maintenance efficiency and production stability and ensure the safe operation of the equipment.

[0153] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0154] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent monitoring method for a thermal shock chamber, characterized in that It includes the following steps: Step S1: Monitor the real-time operating status of the thermal shock chamber, and mine the transient state characteristics at each time point one by one to generate the transient state characteristics at each time node; Step S2: Conduct transient mutation analysis on the transient state characteristics at each time node, and conduct thermal and cold alternating temperature fluctuation analysis to generate cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; Step S3: Conduct state alternating transition analysis on the cold state temperature fluctuation parameters and hot state temperature fluctuation parameters, and conduct dynamic transition trend evolution to generate a thermal and cold alternating state trend evolution map; Step S4: Obtain the operation log of the thermal shock chamber; simulate the thermal and cold alternating shock on the thermal and cold alternating state trend evolution map according to the operation log of the thermal shock chamber, and conduct time-sequence state response recognition to construct thermal and cold alternating response maps for multiple time periods; Step S5: Calculate the temperature rise amplitude of the thermal and cold alternating response maps for multiple time periods, and locate the abnormal state to mark the abnormal time period; Step S6: Predict the abnormal failure probability of the abnormal time period, and make an abnormal failure diagnosis decision to construct a failure decision strategy for the shock chamber to perform real-time state monitoring operations on the thermal shock chamber; Among them, the specific steps of Step S2 are: Step S21: Conduct time-sequence change analysis on the transient state characteristics at each time node to generate transient state change characteristic data; Step S22: Fit the transient state change characteristic data with the transient change time sequence to construct a transient change curve for the shock chamber; Step S23: Conduct transient mutation analysis on the transient change curve of the shock chamber to mark the time stamps of thermal and cold alternating changes; Step S24: Conduct thermal and cold alternating temperature fluctuation analysis on the transient state characteristics at each time node based on the time stamps of thermal and cold alternating changes to generate cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; Among them, the specific steps of Step S3 are: Step S31: Calculate the peak-valley interval of the transient change curve of the shock chamber to obtain the thermal and cold alternating cycle period; Step S32: Calculate the mutation frequency of the transient change curve of the shock chamber to obtain the thermal and cold alternating frequency within the period; Step S33: Mine the alternating transformation logic of the thermal and cold alternating cycle period based on the thermal and cold alternating frequency within the period to generate the thermal and cold alternating transformation rule; Step S34: Conduct state alternating transition analysis on the cold state temperature fluctuation parameters and hot state temperature fluctuation parameters to generate the transition characteristics of the alternating process parameters; Step S35: Conduct dynamic transition trend evolution on the transition characteristics of the alternating process parameters according to the thermal and cold alternating transformation rule to generate a thermal and cold alternating state trend evolution map.

2. The intelligent monitoring method of the thermal shock chamber according to claim 1, characterized in that The specific steps of Step S1 are: Step S11: Monitor the real-time operating status of the thermal shock chamber and collect the operating status monitoring parameters; Step S12: Perform abnormal missing value filling processing on the operating status monitoring parameters to obtain the missing value filled operating status monitoring parameters; Step S13: Conduct multi-time point parameter sampling on the missing value filled operating status monitoring parameters to obtain the operating status monitoring parameters at multiple time nodes; Step S14: Mine the transient state features of the status monitoring parameters at multiple time nodes point by point to generate the transient state features of each time node.

3. The intelligent monitoring method of the thermal shock chamber according to claim 2, wherein The specific steps of Step S12 are as follows: Detect the abnormal state parameters of the operation status monitoring parameters and extract the abnormal state parameters; Perform outlier removal processing based on the abnormal state parameters to obtain the status monitoring parameters after outlier removal; Define the sliding window length value; According to the sliding window length value, divide the status monitoring parameters after outlier removal into time series windows to obtain the status monitoring parameter sequences of multiple time windows; Identify the missing values of the status monitoring parameter sequences of multiple time windows and extract the parameter missing values of each time window; Calculate the parameter average value of each dimension for the status monitoring parameters after outlier removal to obtain the parameter average value of each dimension; Perform linear interpolation to fill the parameter missing values of each time window based on the parameter average value of each dimension to obtain the status monitoring parameters after missing value filling.

4. The intelligent monitoring method of the thermal shock chamber according to claim 1, wherein, The specific steps of Step S4 are as follows: Step S41: Obtain the operation log of the thermal shock chamber; Step S42: Calculate the remaining number of thermal and cold alternations of the operation log of the thermal shock chamber to obtain the remaining number of operation alternations; Step S43: According to the remaining number of operation alternations, perform thermal and cold alternation impact simulation on the thermal and cold alternation state trend evolution map, and collect multi-period parameters to generate the thermal and cold alternation simulation data of multiple time periods; Step S44: Perform time series state response identification on the thermal and cold alternation simulation data of multiple time periods to construct the thermal and cold alternation response maps of multiple time periods.

5. The method according to claim 1, wherein The specific steps of Step S5 are as follows: Step S51: Mine the temperature state of each time period of the thermal and cold alternation response maps of multiple time periods and extract the temperature state features of each time period; Step S52: Calculate the temperature rise amplitude of the temperature state features of each time period to generate the temperature rise amplitude of each time period; Step S53: Analyze the abnormal temperature changes of the temperature rise amplitude of each time period to obtain the abnormal temperature change data; Step S54: Locate the abnormal state based on the abnormal temperature change data and mark the abnormal time period.

6. The intelligent monitoring method of the thermal shock chamber according to claim 1, wherein The specific steps of Step S6 are as follows: Step S61: Infer the abnormal cause of the abnormal time period to obtain the abnormal state factors; Step S62: Predict the abnormal failure probability of the abnormal state factors to obtain the thermal and cold alternation failure prediction probability; Step S63: Perform failure risk analysis based on the thermal and cold alternation failure prediction probability to generate the alternation failure risk data; Step S64: Make an abnormal failure diagnosis decision on the alternation failure risk data to construct the failure decision strategy of the shock chamber; Step S65: Perform intelligent monitoring and protection on the thermal shock chamber based on the failure decision strategy of the shock chamber to execute the real-time status monitoring operation of the thermal shock chamber.

7. An intelligent monitoring system for a thermal shock chamber, characterized in that, A method for intelligent monitoring of a thermal shock chamber for performing the method as claimed in claim 1, comprising: A transient feature mining module for performing real-time operation status monitoring on the thermal shock chamber, mining transient state features point by point, and generating transient state features of each time node; The transient mutation module performs transient mutation analysis on the transient state characteristics at each time node and conducts cold and hot alternating temperature fluctuation analysis, thereby generating cold state temperature fluctuation parameters and hot state temperature fluctuation parameters; The dynamic transition trend module conducts state alternating transition analysis on the cold state temperature fluctuation parameters and the hot state temperature fluctuation parameters and performs dynamic transition trend evolution, thereby generating a cold and hot alternating state trend evolution map; The cold and hot alternating simulation module obtains the operation log of the thermal shock chamber; based on the operation log of the thermal shock chamber, it conducts cold and hot alternating shock simulation on the cold and hot alternating state trend evolution map and performs time series state response recognition to construct cold and hot alternating response maps for multiple time periods; The abnormal state positioning module calculates the temperature rise amplitude of the cold and hot alternating response maps for multiple time periods and conducts abnormal state positioning to mark the abnormal time periods; The fault diagnosis module predicts the abnormal fault probability for the abnormal time periods and makes abnormal fault diagnosis decisions to construct a fault decision strategy for the shock chamber to perform real-time state monitoring operations on the thermal shock chamber.

Images